A Systematic Comparative Study of Machine Learning and Deep Learning Models for Credit Card Fraud Detection

The rapid growth of digital payment systems has significantly increased the risk of credit card fraud, posing major challenges for financial institutions. This study presents a systematic comparative analysis of machine learning and deep learning models for credit card fraud detection using a highly imbalanced dataset from Kaggle. Various models, including Logistic Regression, Decision Tree, Random Forest, XGBoost, Artificial Neural Networks (ANN), and Long Short-Term Memory (LSTM), are implemented and evaluated within a unified experimental framework. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied during data preprocessing. Model performance is assessed using the ROC-AUC metric. The results show that the LSTM model achieves the highest performance. This study highlights the importance of model selection and data preprocessing in improving fraud detection systems.